An adaptive graph convolutional network with residual attention for emotion recognition.

Area of Science:

• Neuroscience
• Artificial Intelligence
• Signal Processing

Background:

• Electroencephalogram (EEG)-based emotion recognition is crucial for understanding human affective states.
• Graph Convolutional Networks (GCNs) excel at analyzing EEG topological features.
• Capturing dynamic topological relationships in EEG data remains a significant challenge.

Purpose of the Study:

• To propose an advanced model for extracting spatio-temporal discriminative features from EEG signals.
• To enhance the accuracy and robustness of emotion recognition using EEG data.
• To address the challenge of capturing dynamic topological relationships in EEG.

Main Methods:

• Developed an adaptive GCN with residual attention (AGC-RSTA) model.
• Constructed an adaptive adjacency matrix within the GCN to capture dynamic spatial topology.
• Employed a residual spatio-temporal attention module for deep feature extraction.

Main Results:

• The proposed AGC-RSTA model achieved high accuracies on benchmark datasets.
• Recognition accuracies reached 94.91% on the SEED dataset.
• Recognition accuracies reached 91.17% on the SEED-IV dataset.
• Demonstrated superior performance compared to existing state-of-the-art methods.

Conclusions:

• The AGC-RSTA model effectively extracts spatio-temporal features for EEG-based emotion recognition.
• The adaptive adjacency matrix and residual attention mechanism significantly improve performance.
• The findings highlight the potential of AGC-RSTA for real-world emotion recognition applications.